Vijay Janapa Reddi 2c9b0dccbf fix: restore Conv2dBackward and MaxPool2dBackward for CNN gradient flow ...

- Restore Conv2dBackward class removed in commit 23c5eb2b5
- Restore MaxPool2dBackward class for pooling gradient routing
- Update Conv2d/MaxPool2d forward() to attach _grad_fn
- Set requires_grad=True on Conv2d weights and bias
- Add enable_autograd() to Module 11 (Embeddings) for progressive disclosure
- Remove skip markers from convolution gradient tests

CNN training now works correctly - conv weights receive gradients and update
during training. All 40 convolution tests pass.

2026-01-24 17:39:11 -05:00

..

test_09_convolutions_progressive.py

fix(tests): resolve import issues and test naming collisions

2026-01-23 17:59:43 -05:00

test_convolutions_core.py

fix: restore Conv2dBackward and MaxPool2dBackward for CNN gradient flow

2026-01-24 17:39:11 -05:00

test_convolutions_gradient_flow.py

fix: restore Conv2dBackward and MaxPool2dBackward for CNN gradient flow

2026-01-24 17:39:11 -05:00